feat: replaced ollama with litellm (#18)

Co-authored-by: Sharang Parnerkar <parnerkarsharang@gmail.com>
Reviewed-on: #18

librechat/librechat.yaml

@@ -1,5 +1,5 @@
 # CERTifAI LibreChat Configuration
-# Ollama backend for self-hosted LLM inference.
+# LiteLLM proxy for unified multi-provider LLM access.
 version: 1.2.8
 
 cache: true
@@ -19,22 +19,16 @@ interface:
 
 endpoints:
   custom:
-    - name: "Ollama"
-      apiKey: "ollama"
-      baseURL: "https://mac-mini-von-benjamin-2:11434/v1/"
+    - name: "LiteLLM"
+      apiKey: "${LITELLM_API_KEY}"
+      baseURL: "https://llm-dev.meghsakha.com/v1/"
       models:
         default:
-          - "llama3.1:8b"
-          - "qwen3:30b-a3b"
+          - "Qwen3-Coder-30B-A3B-Instruct"
         fetch: true
       titleConvo: true
       titleModel: "current_model"
       summarize: false
       summaryModel: "current_model"
       forcePrompt: false
-      modelDisplayLabel: "CERTifAI Ollama"
-      dropParams:
-        - stop
-        - user
-        - frequency_penalty
-        - presence_penalty
+      modelDisplayLabel: "CERTifAI LiteLLM"